Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1707 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.5117. Min Range: -5.5117

Max Act: 5.5117. Min Act: -0.0000

Data Index: 1030659 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 5.5117. Min Range: -5.5117

Max Act: 5.1925. Min Act: -0.0000

Data Index: 855414 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 5.5117. Min Range: -5.5117

Max Act: 4.4012. Min Act: -0.0000

Data Index: 1316251 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 5.5117. Min Range: -5.5117

Max Act: 4.2569. Min Act: -0.0000

Data Index: 307847 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 5.5117. Min Range: -5.5117

Max Act: 4.0956. Min Act: -0.0000

Data Index: 412877 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 5.5117. Min Range: -5.5117

Max Act: 3.9414. Min Act: -0.0000

Data Index: 1205607 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 5.5117. Min Range: -5.5117

Max Act: 4.0919. Min Act: -0.0000

Data Index: 978172 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 5.5117. Min Range: -5.5117

Max Act: 4.0712. Min Act: -0.0000

Data Index: 1167431 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 5.5117. Min Range: -5.5117

Max Act: 4.1502. Min Act: -0.0000

Data Index: 821115 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 5.5117. Min Range: -5.5117

Max Act: 4.1358. Min Act: -0.0000

Data Index: 971395 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 5.5117. Min Range: -5.5117

Max Act: 3.7292. Min Act: -0.0000

Data Index: 758786 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 5.5117. Min Range: -5.5117

Max Act: 3.7251. Min Act: -0.0000

Data Index: 505378 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 5.5117. Min Range: -5.5117

Max Act: 3.6708. Min Act: -0.0000

Data Index: 1268463 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 5.5117. Min Range: -5.5117

Max Act: 3.5581. Min Act: -0.0000

Data Index: 554065 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 5.5117. Min Range: -5.5117

Max Act: 3.6481. Min Act: -0.0000

Data Index: 162893 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 5.5117. Min Range: -5.5117

Max Act: 3.6257. Min Act: -0.0000

Data Index: 335270 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 5.5117. Min Range: -5.5117

Max Act: 3.6061. Min Act: -0.0000

Data Index: 1339637 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 5.5117. Min Range: -5.5117

Max Act: 3.5539. Min Act: -0.0000

Data Index: 708831 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 5.5117. Min Range: -5.5117

Max Act: 3.3728. Min Act: -0.0000

Data Index: 1161165 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 5.5117. Min Range: -5.5117

Max Act: 3.4930. Min Act: -0.0000

Data Index: 1263190 (C4 (Web Text))

Max Activating Token Index: 448